📄 ExpLang: Improved Exploration and Exploitation in LLM Reasoning with On-Policy Thinking Language Selection

Paper · 2026 · Changjiang Gao, Zixian Huang, Kaichen Yang et al.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

🏛️ Institutions

🔬Shanghai Artificial Intelligence LaboratoryShanghai · China117 works · 11,281 citations🎓City University of Hong KongHong Kong · China45 works · 3,014 citations

Also on the byline: Dalian University.

🧭 Fields, topics and concepts

Cite

Cite as Changjiang Gao, Zixian Huang, Kaichen Yang, Jiajun Chen, Jixing Li and Shujian Huang. 2026. ExpLang: Improved Exploration and Exploitation in LLM Reasoning with On-Policy Thinking Language Selection. arXiv:2602.21887.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2602.21887 · arXiv 2602.21887

@misc{gao2026explang,
  title = {{ExpLang: Improved Exploration and Exploitation in LLM Reasoning with On-Policy Thinking Language Selection}},
  author = {Changjiang Gao, Zixian Huang, Kaichen Yang, Jiajun Chen, Jixing Li and Shujian Huang},
  year = {2026},
  doi = {10.48550/arxiv.2602.21887},
  eprint = {2602.21887},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2602.21887}
}

References

40 references, 20 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Andrychowicz, M., Raichuk, A., Stańczyk, P., Orsini, M., Girgin, S., Marinier, R., Hussenot, L., Geist, M., Pietquin, O., Michalski, M., Gelly, S., and Bachem, O. What Matters for On-Policy Deep Actor-Critic Methods? A Large-Scale Study. In International Conference on Learning Representations, Octo… find
2. Barua, J., Eisape, S., Yin, K., and Suhr, A. Long Chain-of-Thought Reasoning Across Languages, October 2025. find
3. Bohnet, B., Dangovski, R., Swersky, K., Moore, S., Chaudhry, A., Kenealy, K., and Fiedel, N. A Comparative Analysis of LLM Adaptation: SFT, LoRA, and ICL in Data-Scarce Scenarios, October 2025. find
4. Chai, L., Yang, J., Sun, T., Guo, H., Liu, J., Wang, B., Liang, X., Bai, J., Li, T., Peng, Q., and Li, Z. xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning, January 2024. find
5. Etxaniz, J., Azkune, G., Soroa, A., Lopez de Lacalle, O., and Artetxe, M. Do Multilingual Language Models Think Better in English? In Duh, K., Gomez, H., and Bethard, S. (eds.), Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human L…
6. Chang, T. A., Arnett, C., Tu, Z., and Bergen, B. When Is Multilinguality a Curse? Language Modeling for 250 High- and Low-Resource Languages. In Al-Onaizan, Y., Bansal, M., and Chen, Y.-N. (eds.), Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 4074–4096,…
7. Faisal, F., Song, K., Wang, S., Ma, S., Liu, S., Deng, H., and Indurthi, S. R. Aligning Multilingual Reasoning with Verifiable Semantics from a High-Resource Expert Model, September 2025. find
8. Chen, K., Zhang, M., and Cao, Y. Less Data Less Tokens: Multilingual Unification Learning for Efficient Test-Time Reasoning in LLMs, June 2025a. find
9. Chen, Z., Qin, X., Wu, Y., Ling, Y., Ye, Q., Zhao, W. X., and Shi, G. Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models, August 2025b. find
10. Gao, C., Huang, X., Zhu, W., Huang, S., Li, L., and Yuan, F. Could Thinking Multilingually Empower LLM Reasoning?, April 2025.
11. Hendrycks, D., Burns, C., Kadavath, S., Arora, A., Basart, S., Tang, E., Song, D., and Steinhardt, J. Measuring Mathematical Problem Solving With the MATH Dataset, November 2021.
12. DeepSeek-AI, Guo, D., Yang, D., Zhang, H., Song, J., Zhang, R., Xu, R., Zhu, Q., Ma, S., Wang, P., Bi, X., Zhang, X., Yu, X., Wu, Y., Wu, Z. F., Gou, Z., Shao, Z., Li, Z., Gao, Z., Liu, A., Xue, B., Wang, B., Wu, B., Feng, B., Lu, C., Zhao, C., Deng, C., Zhang, C., Ruan, C., Dai, D., Chen, D., Ji, D… — LoRA: Low-Rank Adaptation of Large Language Models
13. Hu, P., Liu, S., Gao, C., Huang, X., Han, X., Feng, J., Deng, C., and Huang, S. Large Language Models Are Cross-Lingual Knowledge-Free Reasoners. In Chiruzzo, L., Ritter, A., and Wang, L. (eds.), Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computa… find
14. Nair, A., Zoph, B., Ghorbani, B., Rossen, B., Sokolowsky, B., Barak, B., McGrew, B., Minaiev, B., Hao, B., Baker, B., Houghton, B., McKinzie, B., Eastman, B., Lugaresi, C., Bassin, C., Hudson, C., Li, C. M., de Bourcy, C., Voss, C., Shen, C., Zhang, C., Koch, C., Orsinger, C., Hesse, C., Fischer, C.… find
15. Huang, X., Zhu, W., Hu, H., He, C., Li, L., Huang, S., and Yuan, F. BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models. In Christodoulopoulos, C., Chakraborty, T., Rose, C., and Peng, V. (eds.), Findings of the Association for Computational Linguistics: EMNLP 2025, pp.… find
16. Lai, H. and Nissim, M. mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models. In Ku, L.-W., Martins, A., and Srikumar, V. (eds.), Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 12012–12026, Bangkok, Th…
17. Lightman, H., Kosaraju, V., Burda, Y., Edwards, H., Baker, B., Lee, T., Leike, J., Schulman, J., Sutskever, I., and Cobbe, K. Let’s Verify Step by Step, May 2023. — Let's Verify Step by Step
18. Liu, D. and Niehues, J. Conditions for Catastrophic Forgetting in Multilingual Translation. In Adelani, D. I., Arnett, C., Ataman, D., Chang, T. A., Gonen, H., Raja, R., Schmidt, F., Stap, D., and Wang, J. (eds.), Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025), pp… find
19. Liu, Z., Chen, C., Li, W., Qi, P., Pang, T., Du, C., Lee, W. S., and Lin, M. Understanding R1-Zero-Like Training: A Critical Perspective, October 2025.
20. Muennighoff, N., Yang, Z., Shi, W., Li, X. L., Fei-Fei, L., Hajishirzi, H., Zettlemoyer, L., Liang, P., Candès, E., and Hashimoto, T. S1: Simple test-time scaling, February 2025.
21. OpenAI, Jaech, A., Kalai, A., Lerer, A., Richardson, A., El-Kishky, A., Low, A., Helyar, A., Madry, A., Beutel, A., Carney, A., Iftimie, A., Karpenko, A., Passos, A. T., Neitz, A., Prokofiev, A., Wei, A., Tam, A., Bennett, A., Kumar, A., Saraiva, A., Vallone, A., Duberstein, A., Kondrich, A., Mishch… — Cross-lingual Collapse: How Language-Centric Foundation Models Shape Reasoning in Large Language Models
22. Qi, J., Chen, S., Xiong, Z., Fernández, R., Bitterman, D., and Bisazza, A. When Models Reason in Your Language: Controlling Thinking Language Comes at the Cost of Accuracy. In Christodoulopoulos, C., Chakraborty, T., Rose, C., and Peng, V. (eds.), Findings of the Association for Computational Lingu… find
23. Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E. H., Le, Q. V., and Zhou, D. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. In Advances in Neural Information Processing Systems, October 2022.
24. Wu, Y., Sun, Z., Li, S., Welleck, S., and Yang, Y. Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for LLM Problem-Solving. In The 4th Workshop on Mathematical Reasoning and AI at NeurIPS’24, October 2024. find
25. Rafailov, R., Sharma, A., Mitchell, E., Ermon, S., Manning, C. D., and Finn, C. Direct Preference Optimization: Your Language Model is Secretly a Reward Model, July 2024.
26. Ranaldi, L. and Pucci, G. Multilingual Reasoning via Self-training. In Chiruzzo, L., Ritter, A., and Wang, L. (eds.), Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp. 1… find
27. Xu, S. and Zhang, W. Language of Thought Shapes Output Diversity in Large Language Models, January 2026.
28. Yang, A., Li, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Gao, C., Huang, C., Lv, C., Zheng, C., Liu, D., Zhou, F., Huang, F., Hu, F., Ge, H., Wei, H., Lin, H., Tang, J., Yang, J., Tu, J., Zhang, J., Yang, J., Yang, J., Zhou, J., Zhou, J., Lin, J., Dang, K., Bao, K., Yang, K., Yu, L., Deng,… find
29. Schulman, J., Wolski, F., Dhariwal, P., Radford, A., and Klimov, O. Proximal Policy Optimization Algorithms, August 2017. find
30. Shao, Z., Wang, P., Zhu, Q., Xu, R., Song, J., Bi, X., Zhang, H., Zhang, M., Li, Y. K., Wu, Y., and Guo, D. DeepSeek-Math: Pushing the Limits of Mathematical Reasoning in Open Language Models, April 2024. find
31. Yong, Z.-X., Adilazuarda, M. F., Mansurov, J., Zhang, R., Muennighoff, N., Eickhoff, C., Winata, G. I., Kreutzer, J., Bach, S. H., and Aji, A. F. Crosslingual Reasoning through Test-Time Scaling, May 2025. find
32. She, S., Zou, W., Huang, S., Zhu, W., Liu, X., Geng, X., and Chen, J. MAPO: Advancing Multilingual Reasoning through Multilingual-Alignment-as-Preference Optimization. In Ku, L.-W., Martins, A., and Srikumar, V. (eds.), Proceedings of the 62nd Annual Meeting of the Association for Computational Ling…
33. Yu, Q., Zhang, Z., Zhu, R., Yuan, Y., Zuo, X., YuYue, Dai, W., Fan, T., Liu, G., Liu, J., Liu, L., Liu, X., Lin, H., Lin, Z., Ma, B., Sheng, G., Tong, Y., Zhang, C., Zhang, M., Zhang, R., Zhang, W., Zhu, H., Zhu, J., Chen, J., Chen, J., Wang, C., Yu, H., Song, Y., Wei, X., Zhou, H., Liu, J., Ma, W.-… — DAPO: An Open-Source LLM Reinforcement Learning System at Scale
34. Sheng, G., Zhang, C., Ye, Z., Wu, X., Zhang, W., Zhang, R., Peng, Y., Lin, H., and Wu, C. Hybridflow: A flexible and efficient rlhf framework. arXiv preprint arXiv: 2409.19256, 2024.
35. Zhang, S., Gao, C., Zhu, W., Chen, J., Huang, X., Han, X., Feng, J., Deng, C., and Huang, S. Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners. In Al-Onaizan, Y., Bansal, M., and Chen, Y.-N. (eds.), Proceedings of the 2024 Conference on Empirical Methods in Nat… find
36. Son, G., Yang, D., Patel, H. L., Agarwal, A., Ko, H., Lim, C., Panda, S., Kim, M., Drolia, N., Choi, D., Lee, K.-H., and Yu, Y. Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought, 2025.
37. Sun, H., Min, Y., Chen, Z., Zhao, W. X., Liu, Z., Wang, Z., Fang, L., and Wen, J.-R. Challenging the boundaries of Zhang, X., Liang, Y., Meng, F., Zhang, S., Huang, K., Chen, Y., Xu, J., and Zhou, J. Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning, O…
38. Qwen3-32B. To minimize representation differences caused by multilingual expressions, we first summarize each thinking in a English text that captures its core reasoning. These summaries are embedded using Qwen3-Embedding-8B 8 and clustered using spectral clustering, and the average number of cluste… find
39. Zheng, C., Liu, S., Li, M., Chen, X.-H., Yu, B., Gao, C., Dang, K., Liu, Y., Men, R., Yang, A., Zhou, J., and Lin, J. Group Sequence Policy Optimization, July 2025.
40. Zheng, Y., Zhang, R., Zhang, J., Ye, Y., Luo, Z., Feng, Z., and Ma, Y. Llamafactory: Unified efficient fine-tuning of 100+ language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), Bangkok, Thailand, 2024. Associati…

Updated 31 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/gao-2026-explang-improved-exploration-exploitation-llm/